[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH RFC 0/2] numa: allocate CPUs masks dynamically
From: |
Alexey Kardashevskiy |
Subject: |
Re: [Qemu-devel] [PATCH RFC 0/2] numa: allocate CPUs masks dynamically |
Date: |
Tue, 22 Nov 2016 14:05:27 +1100 |
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.4.0 |
On 22/11/16 05:46, Greg Kurz wrote:
> On Thu, 17 Nov 2016 17:27:20 +1100
> Alexey Kardashevskiy <address@hidden> wrote:
>
>> On 17/11/16 03:02, Igor Mammedov wrote:
>>> This series removes global MAX_CPUMASK_BITS constant
>>> so that it won't inderectly influence maximum CPUs count
>>> supported by different targets.
>>>
>>> It replaces statically allocated bitmasks with dynamically
>>> allocated ones using '-smp maxcpus' value for setting
>>> bitmasks size.
>>> That would allocate just enough memory to handle all
>>> CPUs indexes that a QEMU instance would ever have.
>>>
>>> CC: Alexey Kardashevskiy <address@hidden>
>>> CC: Greg Kurz <address@hidden>
>>> CC: David Gibson <address@hidden>
>>> CC: Eduardo Habkost <address@hidden>
>>> CC: Paolo Bonzini <address@hidden>
>>>
>>>
>>> Igor Mammedov (2):
>>> add bitmap_free() wrapper
>>> numa: make -numa parser dynamically allocate CPUs masks
>>
>> Nice, with "ulimit -n 3072", guest kernel with CONFIG_NR_CPUS=2048,
>> "mc->max_cpus = 2048;" in hw/ppc/spapr.c, and "-smp 2048,threads=8" in
>> QEMU cmdline, I get all 2048 CPUs in the guest.
>>
>
> Nice ! And mc->max_cpus in hw/ppc/spapr.c no longer depends on
> MAX_CPUMASK_BITS since commit 079019f2e319b, so it is already
> possible to bump that value (1024 ? 2048 ?).
>
> Will you send a patch ?
Sure, when these two hit upstream.
>
>>
>> Tested-by: Alexey Kardashevskiy <address@hidden>
>>
>>
>>>
>>> include/qemu/bitmap.h | 5 +++++
>>> include/sysemu/numa.h | 2 +-
>>> include/sysemu/sysemu.h | 7 -------
>>> numa.c | 19 ++++++++++++-------
>>> vl.c | 5 -----
>>> 5 files changed, 18 insertions(+), 20 deletions(-)
>>>
>>
>>
>
--
Alexey